CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-automation-recommender

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Well-structured and actionable with excellent progressive disclosure, but weakened by verbose padding in the Phase 0 confirmation ceremony and redundant decision-framework prose. Tightening those sections and adding a recommendation-verification checkpoint would raise it further.

Suggestions

Trim the Phase 0 'Cherry Studio addition' section to a single concise confirmation checkpoint, removing the bilingual example phrasing, token-budget prose, and multi-branch decline alternatives.

Merge the 'Decision Framework' section into the existing signal-to-recommendation tables, which already encode the same when-to-recommend logic, to eliminate redundancy.

Add a brief validation step in Phase 2 or 3 requiring that each surfaced recommendation map to a concrete detected codebase signal before it is included in the report.

DimensionReasoningScore

Conciseness

The signal-to-recommendation tables are efficient and earn their tokens, but the bilingual Phase 0 'Cherry Studio addition' confirmation ceremony and the Decision Framework (which restates what the tables already convey) add noticeable padding.

3 / 5

Actionability

Provides executable bash inspection commands, concrete install commands ('claude mcp add context7'), file paths, and yaml/settings.json examples, with only minor gaps such as missing example web-search queries for library-specific recommendations.

4 / 5

Workflow Clarity

Phases 0 through 3 are clearly sequenced with a confirmation gate in Phase 0; being read-only, the destructive-ops cap does not apply, though a step verifying each recommendation maps to a detected signal is absent.

4 / 5

Progressive Disclosure

The body is a clean overview that delegates detailed patterns to five well-signaled, one-level-deep reference files (e.g. 'See [references/mcp-servers.md]'), all of which exist, keeping navigation easy and content appropriately split.

5 / 5

Total

16

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states a concrete capability with an enumerated scope, provides an explicit 'Use when...' trigger clause full of natural user phrasings, and carves out a distinct recommender niche. No meaningful gaps in what or when.

DimensionReasoningScore

Specificity

States the concrete action ('Analyze a codebase and recommend Claude Code automations') and enumerates five specific automation types (hooks, subagents, skills, plugins, MCP servers), giving comprehensive coverage of the skill's output scope.

5 / 5

Completeness

Explicitly answers both 'what' (analyze a codebase and recommend automations across five categories) and 'when' (a concrete 'Use when...' clause with several trigger phrases), matching the top anchor.

5 / 5

Trigger Term Quality

The 'Use when...' clause supplies multiple natural phrases users would actually say ('automation recommendations', 'optimize their Claude Code setup', 'improving Claude Code workflows', 'set up Claude Code for a project', 'what Claude Code features they should use').

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (recommending Claude Code extensibility automations) with distinct triggers tied to setup/optimization requests, making conflict with other skills unlikely.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
CherryHQ/cherry-studio
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.